{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2MDMPGP62TTQJCL7UZDY33PYPJ","short_pith_number":"pith:2MDMPGP6","schema_version":"1.0","canonical_sha256":"d306c799fed4e704897fa6478dedf87a511033c7390e32a247a207eecf0b284a","source":{"kind":"arxiv","id":"2607.05121","version":1},"attestation_state":"computed","paper":{"title":"From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Amal Akli, Cedric Richter, Melissa Akli, Mike Papadakis, Yves Le Traon","submitted_at":"2026-07-06T14:10:56Z","abstract_excerpt":"Large language models are known to be sensitive to prompt formulation. Even minor variations in wording can substantially degrade performance. This sensitivity reveals an opportunity: if prompt phrasing can harm performance, can it be used to improve it? To investigate this question, we introduce a search-based approach that identifies and evolves a set of natural language transformation rules with strong downstream effects on coding performance. We then propose DUALFIX, a staged repair pipeline that combines the evolved transformation rules with execution-feedback repair, addressing both spec"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.05121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-06T14:10:56Z","cross_cats_sorted":[],"title_canon_sha256":"0bc290d854d5a023b0df0004d5240522d49469d5a0d432dcf592e516d316ab63","abstract_canon_sha256":"411b6c15c57017069870160cb7a6f50f03a1141dfa9a4f3a4af17521ab65a80b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:16.766367Z","signature_b64":"ZFJ7XfIzIIN29mBGA+KCJrz+Yf8r0QFucXxQTPpFMKnX0w86pfOW7EriMRfLOyD2skb+musdNyQJ/Z3B7vIfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d306c799fed4e704897fa6478dedf87a511033c7390e32a247a207eecf0b284a","last_reissued_at":"2026-07-07T03:19:16.765942Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:16.765942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Amal Akli, Cedric Richter, Melissa Akli, Mike Papadakis, Yves Le Traon","submitted_at":"2026-07-06T14:10:56Z","abstract_excerpt":"Large language models are known to be sensitive to prompt formulation. Even minor variations in wording can substantially degrade performance. This sensitivity reveals an opportunity: if prompt phrasing can harm performance, can it be used to improve it? To investigate this question, we introduce a search-based approach that identifies and evolves a set of natural language transformation rules with strong downstream effects on coding performance. We then propose DUALFIX, a staged repair pipeline that combines the evolved transformation rules with execution-feedback repair, addressing both spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05121","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.05121/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.05121","created_at":"2026-07-07T03:19:16.765993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05121v1","created_at":"2026-07-07T03:19:16.765993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05121","created_at":"2026-07-07T03:19:16.765993+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MDMPGP62TTQ","created_at":"2026-07-07T03:19:16.765993+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MDMPGP62TTQJCL7","created_at":"2026-07-07T03:19:16.765993+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MDMPGP6","created_at":"2026-07-07T03:19:16.765993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ","json":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ.json","graph_json":"https://pith.science/api/pith-number/2MDMPGP62TTQJCL7UZDY33PYPJ/graph.json","events_json":"https://pith.science/api/pith-number/2MDMPGP62TTQJCL7UZDY33PYPJ/events.json","paper":"https://pith.science/paper/2MDMPGP6"},"agent_actions":{"view_html":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ","download_json":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ.json","view_paper":"https://pith.science/paper/2MDMPGP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05121&json=true","fetch_graph":"https://pith.science/api/pith-number/2MDMPGP62TTQJCL7UZDY33PYPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2MDMPGP62TTQJCL7UZDY33PYPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ/action/storage_attestation","attest_author":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ/action/author_attestation","sign_citation":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ/action/citation_signature","submit_replication":"https://pith.science/pith/2MDMPGP62TTQJCL7UZDY33PYPJ/action/replication_record"}},"created_at":"2026-07-07T03:19:16.765993+00:00","updated_at":"2026-07-07T03:19:16.765993+00:00"}